© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22646
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _IMPLEMENT
    -0.08
    ä½łçļĦæľĭåıĭ
    -0.08
    æĪijçļĦæľĭåıĭ
    -0.08
    ossi
    -0.08
    hap
    -0.08
    mert
    -0.07
    asher
    -0.07
    .pop
    -0.07
    agli
    -0.07
     lord
    -0.07
    POSITIVE LOGITS
    ink
    0.07
    à¸łà¸²
    0.06
    okit
    0.06
     ÙĨÙĩ
    0.06
    amp
    0.06
    æĿı
    0.06
    Enumerator
    0.06
    ริà¸ĩ
    0.06
    ade
    0.06
    ki
    0.06
    Activations Density 0.000%

    No Known Activations